#!/usr/bin/env python3
"""mutation_boundary.py — cognitive-stage mutation boundary (D5, #284).

D5.1-D5.3 tightening (2026-09-09):

D5.1 CONTENT FINGERPRINTS, not porcelain-line diffs.
  Pre-existing dirty files can hide further mutations if we only compare
  "which paths changed" — a file already modified before the stage can be
  modified again during it, producing the same porcelain line. The boundary
  now captures a content hash per tracked/untracked file and compares hashes;
  a change to an already-dirty file is detected.

D5.2 EXPLICIT PER-STAGE ALLOWLIST, not artifact_dir-wide.
  The executor passes exactly the paths the stage may write: its declared
  artifact file, its event/log files, telemetry. NOT the whole artifact_dir
  (which would let an OUTWARD worker silently modify another stage's
  artifact or the task-tree authority).

D5.3 VERIFY ON EVERY TERMINAL PATH.
  The mutation check runs for COMPLETED, GATE_FAILED, GATE_RETRY, FAILED,
  TIMEOUT and INTERRUPTED attempts — a worker that mutates source and then
  fails must still have that mutation identified.

Clean-worktree requirement (D5.1 corollary): the canonical baseline requires
a clean worktree before cognitive execution. If the worktree is dirty at
capture time, the caller must decide (abort or accept-and-fingerprint).
This module fingerprints regardless, so even a dirty worktree can't hide
in-stage mutations.
"""

from __future__ import annotations

import hashlib
import os
import subprocess


class MutationError(RuntimeError):
    """Raised when a cognitive stage mutated source outside its authority."""


def _git(*args: str, cwd: str) -> str:
    result = subprocess.run(["git", *args], cwd=cwd, capture_output=True, text=True, timeout=30)
    return result.stdout.strip()


def capture_worktree_state(repo_root: str) -> dict:
    """D5.1: content fingerprints per file, not just porcelain lines.

    Captures a {relative_path: content_hash} map for every tracked and
    untracked file in the repo (excluding .git/), plus HEAD.
    Called before cognition.
    """
    state: dict = {}
    try:
        state["head"] = _git("rev-parse", "HEAD", cwd=repo_root)
        state["worktree_clean"] = _git("status", "--porcelain", cwd=repo_root) == ""
        # All files (tracked + untracked, excluding .git)
        files = _git("ls-files", "--cached", "--others", "--exclude-standard", cwd=repo_root)
        fingerprints = {}
        for f in files.splitlines():
            fp = os.path.join(repo_root, f)
            if os.path.isfile(fp):
                try:
                    h = hashlib.sha256(open(fp, "rb").read()).hexdigest()
                    fingerprints[os.path.normpath(f)] = h
                except OSError:
                    fingerprints[os.path.normpath(f)] = "UNREADABLE"
        state["fingerprints"] = fingerprints
    except (OSError, subprocess.SubprocessError, subprocess.TimeoutExpired) as e:
        state["error"] = str(e)
    return state


def verify_no_source_mutation(repo_root: str, before: dict, allowed_paths: list[str]) -> list[str]:
    """D5.1+D5.2: content-hash comparison + explicit allowlist.

    Returns violations (empty = clean).

    allowed_paths: EXPLICIT relative paths this stage may write — NOT a
    directory-wide grant. Each entry is either an exact file path or a
    directory prefix ending in '/' (e.g. "research/issue-162-b3v2/telemetry/").
    """
    violations = []
    after = capture_worktree_state(repo_root)
    if "error" in before or "error" in after:
        return violations  # can't verify in a broken-git env — don't false-positive

    before_fp: dict = before.get("fingerprints", {})
    after_fp: dict = after.get("fingerprints", {})

    # Normalize allowed paths: exact files or directory prefixes
    allowed_exact = set()
    allowed_prefixes = set()
    for p in allowed_paths:
        norm = os.path.normpath(p)
        if p.endswith("/"):
            allowed_prefixes.add(norm)
        else:
            allowed_exact.add(norm)

    def _is_allowed(rel: str) -> bool:
        if rel in allowed_exact:
            return True
        return any(rel.startswith(prefix + os.sep) or rel.startswith(prefix + "/") for prefix in allowed_prefixes)

    # D5.1: compare fingerprints — detects changes to already-dirty files
    for path in sorted(set(before_fp) | set(after_fp)):
        if _is_allowed(path):
            continue
        old = before_fp.get(path)
        new = after_fp.get(path)
        if old is None and new is not None:
            violations.append(f"UNAUTHORIZED_MUTATION: new file {path}")
        elif old is not None and new is None:
            violations.append(f"UNAUTHORIZED_MUTATION: deleted {path}")
        elif old != new and old is not None and new is not None:
            violations.append(f"UNAUTHORIZED_MUTATION: content changed {path}")

    # HEAD must not move (cognitive stages must never commit)
    if before.get("head") and after.get("head") and before["head"] != after["head"]:
        violations.append(f"UNAUTHORIZED_COMMIT: HEAD moved {before['head'][:8]} → {after['head'][:8]}")

    return violations


def require_clean_worktree(repo_root: str) -> tuple[bool, str]:
    """D5.1 corollary: canonical cognitive execution requires a clean worktree.
    Returns (clean, status_output). The caller decides: abort or
    accept-and-fingerprint. Dirty worktrees can't hide mutations (fingerprints
    still work) but the baseline methodology requires clean starts."""
    status = _git("status", "--porcelain", cwd=repo_root)
    return (status == "", status)